AI Agent - arXivDaily 专题

2506.08961 2025-06-11 cs.LG cs.AI 62%

Towards Robust Deep Reinforcement Learning against Environmental State Perturbation

Chenxu Wang, Huaping Liu

机构 * Department of Computer Science and Technology, Tsinghua University（计算机科学与技术系，清华大学）

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

2503.04256 2025-06-09 cs.LG cs.AI 62%

Knowledge Retention for Continual Model-Based Reinforcement Learning

Yixiang Sun, Haotian Fu, Michael Littman, George Konidaris

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

2310.13391 2025-06-03 cs.LG cs.AI cs.NE 62%

Learning Successor Features with Distributed Hebbian Temporal Memory

Evgenii Dzhivelikian, Petr Kuderov, Aleksandr I. Panov

机构 * MIPT（莫斯科物理技术学院）； AIRI（人工智能研究所）

专题命中记忆与上下文管理：planning(abstract)；分类 cs.AI、cs.LG

Comments Poster on ICLR 2025

2505.23815 2025-06-02 cs.CL cs.LG 62%

Aligning LLMs by Predicting Preferences from User Writing Samples

Stéphane Aroca-Ouellette, Natalie Mackraz, Barry-John Theobald, Katherine Metcalf

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL、cs.LG

Comments Accepted to ICML 2025. 32 pages total: 9 main, 2 references, 21 appendix. arXiv admin note: substantial text overlap with arXiv:2410.06273

2310.08731 2025-05-29 cs.AI cs.LG cs.SY eess.SY 62%

Novelty Detection in Reinforcement Learning with World Models

Geigh Zollicoffer, Kenneth Eaton, Jonathan Balloch, Julia Kim, Wei Zhou, Robert Wright, Mark O. Riedl

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments ICML Spotlight 2025

2505.19206 2025-05-27 cs.CL cs.LG cs.SD eess.AS 62%

SpeakStream: Streaming Text-to-Speech with Interleaved Data

Richard He Bai, Zijin Gu, Tatiana Likhomanenko, Navdeep Jaitly

机构 * Apple（苹果公司）

专题命中记忆与上下文管理：AI agent(abstract)；分类 cs.CL、cs.LG

2505.10838 2025-05-19 cs.LG cs.CL cs.CR 62%

LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs

Ran Li, Hao Wang, Chengzhi Mao

机构 * Columbia University（哥伦比亚大学）； Rutgers University（罗格斯大学）

专题命中记忆与上下文管理：agentic(abstract)；分类 cs.CL、cs.LG

2505.05177 2025-05-09 cs.AI cs.LG 62%

MARK: Memory Augmented Refinement of Knowledge

Anish Ganguli, Prabal Deb, Debleena Banerjee

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

2505.03817 2025-05-08 cs.CR cs.AI cs.LG 62%

Modeling Behavioral Preferences of Cyber Adversaries Using Inverse Reinforcement Learning

Aditya Shinde, Prashant Doshi

机构 * THINC Lab, School of Computing, University of Georgia（THINC实验室，计算学院，佐治亚大学）

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

2408.11816 2025-04-15 cs.LG cs.AI 62%

Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction

Anthony GX-Chen, Kenneth Marino, Rob Fergus

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments ICLR 2025

2504.08779 2025-04-15 cs.CL cs.AI 62%

Can AI Master Construction Management (CM)? Benchmarking State-of-the-Art Large Language Models on CM Certification Exams

Ruoxin Xiong, Yanyu Wang, Suat Gunhan, Yimin Zhu, Charles Berryman

专题命中记忆与上下文管理：workflow(abstract)；分类 cs.AI、cs.CL

2408.02349 2025-04-09 cs.LG cs.AI 62%

Toward Cost-efficient Adaptive Clinical Trials in Knee Osteoarthritis with Reinforcement Learning

Khanh Nguyen, Huy Hoang Nguyen, Egor Panfilov, Aleksei Tiulpin

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

2504.03861 2025-04-08 cs.AI cs.LG 62%

Improving World Models using Deep Supervision with Linear Probes

Andrii Zahorodnii

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments ICLR 2025 Workshop on World Models

2504.02252 2025-04-04 cs.LG cs.AI cs.RO 62%

Adapting World Models with Latent-State Dynamics Residuals

JB Lanier, Kyungmin Kim, Armin Karamzade, Yifei Liu, Ankita Sinha, Kat He, Davide Corsi, Roy Fox

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments 15 pages, 11 figures. Project website at https://redraw.jblanier.net/

2411.18305 2025-03-28 eess.SY cs.AI cs.LG cs.SY 62%

Application of Soft Actor-Critic Algorithms in Optimizing Wastewater Treatment with Time Delays Integration

Esmaeel Mohammadi, Daniel Ortiz-Arroyo, Aviaja Anna Hansen, Mikkel Stokholm-Bjerregaard, Sebastien Gros, Akhil S Anand, Petar Durdevic

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Journal ref Expert Systems with Applications Volume 277, 5 June 2025, 127180

2503.20844 2025-03-28 cs.LG cs.AI cs.NI cs.RO 62%

Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks

Zongyuan Zhang, Tianyang Duan, Zheng Lin, Dong Huang, Zihan Fang, Zekai Sun, Ling Xiong, Hongbin Liang, Heming Cui, Yong Cui, Yue Gao

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments 9 pages, 6 figures

2503.20613 2025-03-27 cs.LG cs.AI cs.NI cs.SY eess.SY 62%

State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning

Zongyuan Zhang, Tianyang Duan, Zheng Lin, Dong Huang, Zihan Fang, Zekai Sun, Ling Xiong, Hongbin Liang, Heming Cui, Yong Cui

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments 15 pages, 11 figures

2409.05358 2025-03-25 cs.LG cs.AI 62%

BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping

Aly Lidayan, Michael Dennis, Stuart Russell

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments Published at ICLR 2025

2503.14554 2025-03-20 cs.RO cs.AI cs.CV cs.LG 62%

Synchronous vs Asynchronous Reinforcement Learning in a Real World Robot

Ali Parsaee, Fahim Shahriar, Chuxin He, Ruiqing Tan

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments Presented at Alberta Robotics & Intelligent Systems Expo (RISE) Conference

2503.12053 2025-03-18 cs.LG cs.AI 62%

Ferret: An Efficient Online Continual Learning Framework under Varying Memory Constraints

Yuhao Zhou, Yuxin Tian, Jindi Lv, Mingjia Shi, Yuanxi Li, Qing Ye, Shuhao Zhang, Jiancheng Lv

专题命中记忆与上下文管理：planning(abstract)；分类 cs.AI、cs.LG

Comments CVPR 2025

2405.06682 2025-03-17 cs.CL cs.AI 62%

Self-Reflection in LLM Agents: Effects on Problem-Solving Performance

Matthew Renze, Erhan Guven

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.CL

Journal ref 2nd International Conference on Foundation and Large Language Models (FLLM 2024), pp. 476-483

2503.08102 2025-03-13 cs.AI cs.CL cs.HC 62%

AI-native Memory 2.0: Second Me

Jiale Wei, Xiang Ying, Tao Gao, Fangyi Bao, Felix Tao, Jingbo Shang

专题命中记忆与上下文管理：AI agent(abstract)；分类 cs.AI、cs.CL

2502.20168 2025-02-28 cs.RO cs.AI cs.LG cs.NE stat.ML 62%

Accelerating Model-Based Reinforcement Learning with State-Space World Models

Maria Krinner, Elie Aljalbout, Angel Romero, Davide Scaramuzza

专题命中记忆与上下文管理：planning(abstract)；分类 cs.AI、cs.LG

2502.13200 2025-02-20 cs.LG cs.AI 62%

Learning To Explore With Predictive World Model Via Self-Supervised Learning

Alana Santana, Paula P. Costa, Esther L. Colombini

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

2502.10200 2025-02-17 cs.LG cs.AI cs.NE 62%

Dynamic Reinforcement Learning for Actors

Katsunari Shibata

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments 31 pages, 20 figures

2403.16527 2025-02-12 cs.AI cs.CL cs.RO 62%

Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the Art

Neeloy Chakraborty, Melkior Ornik, Katherine Driggs-Campbell

专题命中记忆与上下文管理：planning(abstract)；分类 cs.AI、cs.CL

Comments Accepted to ACM Computing Surveys; 55 pages, 5 tables, 3 figures

2502.02265 2025-02-05 cs.LG cs.AI 62%

Adviser-Actor-Critic: Eliminating Steady-State Error in Reinforcement Learning Control

Donghe Chen, Yubin Peng, Tengjie Zheng, Han Wang, Chaoran Qu, Lin Cheng

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments 13 pages, 9 figures

2409.16791 2025-02-05 cs.LG cs.AI 62%

Symbolic State Partitioning for Reinforcement Learning

Mohsen Ghaffari, Mahsa Varshosaz, Einar Broch Johnsen, Andrzej Wąsowski

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

2501.15355 2025-01-28 cs.CL cs.AI 62%

Large Language Models as Theory of Mind Aware Generative Agents with Counterfactual Reflection

Bo Yang, Jiaxian Guo, Yusuke Iwasawa, Yutaka Matsuo

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.CL

2406.05027 2025-01-28 cs.LG cs.AI 62%

Optimizing Automatic Differentiation with Deep Reinforcement Learning

Jamie Lohoff, Emre Neftci

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI、cs.LG

Comments Accepted as a spotlight paper at NeurIPS 2024

Journal ref Proceedings of the 38th Conference on Neural Information Processing Systems. 2024

1. 记忆与上下文管理 4753 篇

Towards Robust Deep Reinforcement Learning against Environmental State Perturbation

Knowledge Retention for Continual Model-Based Reinforcement Learning

Learning Successor Features with Distributed Hebbian Temporal Memory

Aligning LLMs by Predicting Preferences from User Writing Samples

Novelty Detection in Reinforcement Learning with World Models

SpeakStream: Streaming Text-to-Speech with Interleaved Data

LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs

MARK: Memory Augmented Refinement of Knowledge

Modeling Behavioral Preferences of Cyber Adversaries Using Inverse Reinforcement Learning

Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction

Can AI Master Construction Management (CM)? Benchmarking State-of-the-Art Large Language Models on CM Certification Exams

Toward Cost-efficient Adaptive Clinical Trials in Knee Osteoarthritis with Reinforcement Learning

Improving World Models using Deep Supervision with Linear Probes

Adapting World Models with Latent-State Dynamics Residuals

Application of Soft Actor-Critic Algorithms in Optimizing Wastewater Treatment with Time Delays Integration

Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks

State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning

BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping

Synchronous vs Asynchronous Reinforcement Learning in a Real World Robot

Ferret: An Efficient Online Continual Learning Framework under Varying Memory Constraints

Self-Reflection in LLM Agents: Effects on Problem-Solving Performance

AI-native Memory 2.0: Second Me

Accelerating Model-Based Reinforcement Learning with State-Space World Models

Learning To Explore With Predictive World Model Via Self-Supervised Learning

Dynamic Reinforcement Learning for Actors

Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the Art

Adviser-Actor-Critic: Eliminating Steady-State Error in Reinforcement Learning Control

Symbolic State Partitioning for Reinforcement Learning

Large Language Models as Theory of Mind Aware Generative Agents with Counterfactual Reflection

Optimizing Automatic Differentiation with Deep Reinforcement Learning